© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96606
    Prev
    Next
    INDEX
    Explanations

    code structures and access modifiers in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASA
    -0.07
    anus
    -0.07
     mills
    -0.06
    hw
    -0.06
    gw
    -0.06
    tod
    -0.06
    ÑģÑıÑĩ
    -0.06
    lick
    -0.06
    alc
    -0.06
    zc
    -0.06
    POSITIVE LOGITS
     Anton
    0.07
    ripp
    0.07
    IFS
    0.07
    arios
    0.06
    layan
    0.06
    cel
    0.06
    ffen
    0.06
    coon
    0.06
     khuôn
    0.06
     herself
    0.06
    Activations Density 0.051%

    No Known Activations